Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Visualization Toolbox for Long Short Term Memory networks (LSTMs)
| Date | Stars |
|---|---|
| 2026-07-24 | 1265 |
| 2026-07-25 | 1265 |
| 2026-07-28 | 1265 |
| 2026-07-30 | 1265 |
| 2026-08-06 | 1265 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
#  Visual Analysis for State Changes in RNNs
More information about LSTMVis, an introduction video, and the link to the live demo can be found at **[lstm.seas.harvard.edu](http://lstm.seas.harvard.edu)**
Also check out our new work on Sequence-to-Sequence models on [github](https://github.com/hendrikstrobelt/seq2seq-vis) or the live demo at **[http://seq2seq-vis.io/](http://seq2seq-vis.io/)**
<div style='text-align:center'>
<img src="docs/img/teaser_V2.png" />
</div>
## Changes in V2.1
- update to Python 3.7++ (thanks to @nneophyt)
## Changes in V2
- new design and server-backend
- discrete zooming for hidden-state track
- added annotation tracks for meta-data and prediction
- added training and extraction workflow for tensorflow
- client is now ES6 and D3v4
- some performance enhancements on client side
- Added Keras tutorial [here](docs/keras.md) (thanks to Mohammadreza Ebrahimi)
## Install
Please use **python 3.7 or later** to install LSTMVis.
Clone the repository:
```bash
git clone https://github.com/HendrikStrobelt/LSTMVis.git; cd LSTMVis
```
Install python (server-side) requirements using [pip](https://pip.pypa.io/en/stable/installing/):
```bash
python -m venv venv3
source venv3/bin/activate
pip install -r requirements.txt
```
<!--Install [bower](https://bower.io/) (client side) requirements:
```bash
cd client; bower install; cd ..
```-->
Download & Unzip example dataset(s) into `<LSTMVis>/data/05childbook`:
[Children Book - Gutenberg](https://drive.google.com/file/d/0B542UFSlrvMjMHcxWHluNzh3clU/view?usp=sharing) - 2.2 GB
[Parens Dataset - 10k small](https://drive.google.com/file/d/0B3yX0IkfCkLvWUowazhOZHFuSms/view?usp=sharing&resourcekey=0-JPmD2S5SFne6iTyOzAT3_w) - 0.03 GB
start server:
```bash
source venv3/bin/activate
python lstm_server.py -dir <datadir>
```
For the example dataset, use `python lstm_server.py -dir data`
open browser at [http://localhost:8888](http://localhost:8888/client/index.html) - eh voila !
## Adding Your Own Data
If you want to train your own data first, please read the [Training](docs/chapter/train.md) document. If you have your own data at hand, adding it to LSTMVis is very easy. You only need three files:
* HDF5 file containing the state vectors for each time step (e.g. `states.hdf5`)
* HDF5 file containing a word ID for each time step (e.g. `train.hdf5`)*
* Dict file containing the mapping from word ID to word (e.g. `train.dict`)*
A schematic representation of the data:
*If you don't have these files yet, but a space-separated `.txt` file of your training data instead, check out our [text conversion tool](docs/chapter/tools.md#convert-.txt-to-.h5-and-.dict)
### Data Directory
LSTMVis parses all subdirectories of `<datadir>` for config files `lstm.yml`.
A typical `<datadir>` might look like this:
```
<datadir>
├── paren <--- project directory
│ ├── lstm.yml <--- config file
│ ├── states.hdf5 <--- states for each time step
│ ├── train.hdf5 <--- word ID for each time step
│ └── train.dict <--- mapping word ID -> word
├── fun ..
```
### Config File
a simple example of an `lstm.yml` is:
```yaml
name: children books # project name
description: children book texts from the Gutenberg project # little description
files: # assign files to reference name
states: states.hdf5 # HDF5 files have to end with .h5 or .hdf5 !!!
train: train.hdf5 # word ids of training set
words: train.dict # dict files have to end with .dict !!
word_sequence: # defines the word sequence
file: train # HDF5 file
path: word_ids # path to table in HDF5
dict_file: words # dictionary to map IDs from HDF5 to words
states: # section to define which states of your model you want to look at
file: states # HDF5 files containing the state for each position
types: [
{type: state, layer: 1, path: states1}, # type={state, output}, layer=[1..x], path = HDF5 path
{type: stExcerpt of 4,699 characters
Read on GitHub
133
Sebastian Gehrmann · Google · United States
36
Sasha Rush · Cursor · United States
7
M. Ernestus · Germany
2
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:a5f78420f03f83f2, topic:neural-network